From dc20f3244ae920430d9d9f19939a13a0279380ca Mon Sep 17 00:00:00 2001 From: Andrey Ryabinin Date: Thu, 9 Jun 2016 15:20:05 +0300 Subject: kernel/sysrq, watchdog, sched/core: Reset watchdog on all CPUs while processing sysrq-w commit 57675cb976eff977aefb428e68e4e0236d48a9ff upstream. Lengthy output of sysrq-w may take a lot of time on slow serial console. Currently we reset NMI-watchdog on the current CPU to avoid spurious lockup messages. Sometimes this doesn't work since softlockup watchdog might trigger on another CPU which is waiting for an IPI to proceed. We reset softlockup watchdogs on all CPUs, but we do this only after listing all tasks, and this may be too late on a busy system. So, reset watchdogs CPUs earlier, in for_each_process_thread() loop. Signed-off-by: Andrey Ryabinin Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/1465474805-14641-1-git-send-email-aryabinin@virtuozzo.com Signed-off-by: Ingo Molnar Signed-off-by: Greg Kroah-Hartman --- kernel/sched/core.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 6c0cdb5a73f8..67d1e1597d9c 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -4951,14 +4951,16 @@ void show_state_filter(unsigned long state_filter) /* * reset the NMI-timeout, listing all files on a slow * console might take a lot of time: + * Also, reset softlockup watchdogs on all CPUs, because + * another CPU might be blocked waiting for us to process + * an IPI. */ touch_nmi_watchdog(); + touch_all_softlockup_watchdogs(); if (!state_filter || (p->state & state_filter)) sched_show_task(p); } - touch_all_softlockup_watchdogs(); - #ifdef CONFIG_SCHED_DEBUG sysrq_sched_debug_show(); #endif -- cgit v1.2.3 From 75d6026fd7d605a668ef532193c2bae707a4316c Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 26 May 2016 15:42:13 -0400 Subject: cgroup: set css->id to -1 during init commit 8fa3b8d689a54d6d04ff7803c724fb7aca6ce98e upstream. If percpu_ref initialization fails during css_create(), the free path can end up trying to free css->id of zero. As ID 0 is unused, it doesn't cause a critical breakage but it does trigger a warning message. Fix it by setting css->id to -1 from init_and_link_css(). Signed-off-by: Tejun Heo Cc: Wenwei Tao Fixes: 01e586598b22 ("cgroup: release css->id after css_free") Signed-off-by: Tejun Heo Signed-off-by: Greg Kroah-Hartman --- kernel/cgroup.c | 1 + 1 file changed, 1 insertion(+) (limited to 'kernel') diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 1c9d701f7a72..a3424f28aaf4 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -4793,6 +4793,7 @@ static void init_and_link_css(struct cgroup_subsys_state *css, memset(css, 0, sizeof(*css)); css->cgroup = cgrp; css->ss = ss; + css->id = -1; INIT_LIST_HEAD(&css->sibling); INIT_LIST_HEAD(&css->children); css->serial_nr = css_serial_nr_next++; -- cgit v1.2.3 From 34bf12312bd4222a1b945be3f58173edc8aa3f22 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Fri, 24 Jun 2016 15:53:54 +0200 Subject: sched/fair: Fix effective_load() to consistently use smoothed load commit 7dd4912594daf769a46744848b05bd5bc6d62469 upstream. Starting with the following commit: fde7d22e01aa ("sched/fair: Fix overly small weight for interactive group entities") calc_tg_weight() doesn't compute the right value as expected by effective_load(). The difference is in the 'correction' term. In order to ensure \Sum rw_j >= rw_i we cannot use tg->load_avg directly, since that might be lagging a correction on the current cfs_rq->avg.load_avg value. Therefore we use tg->load_avg - cfs_rq->tg_load_avg_contrib + cfs_rq->avg.load_avg. Now, per the referenced commit, calc_tg_weight() doesn't use cfs_rq->avg.load_avg, as is later used in @w, but uses cfs_rq->load.weight instead. So stop using calc_tg_weight() and do it explicitly. The effects of this bug are wake_affine() making randomly poor choices in cgroup-intense workloads. Signed-off-by: Peter Zijlstra (Intel) Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Fixes: fde7d22e01aa ("sched/fair: Fix overly small weight for interactive group entities") Signed-off-by: Ingo Molnar Signed-off-by: Greg Kroah-Hartman --- kernel/sched/fair.c | 15 +++++++++------ 1 file changed, 9 insertions(+), 6 deletions(-) (limited to 'kernel') diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 51c615279b23..b8b516c37bf1 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -687,8 +687,6 @@ void init_entity_runnable_average(struct sched_entity *se) /* when this task enqueue'ed, it will contribute to its cfs_rq's load_avg */ } -static inline unsigned long cfs_rq_runnable_load_avg(struct cfs_rq *cfs_rq); -static inline unsigned long cfs_rq_load_avg(struct cfs_rq *cfs_rq); #else void init_entity_runnable_average(struct sched_entity *se) { @@ -4594,19 +4592,24 @@ static long effective_load(struct task_group *tg, int cpu, long wl, long wg) return wl; for_each_sched_entity(se) { - long w, W; + struct cfs_rq *cfs_rq = se->my_q; + long W, w = cfs_rq_load_avg(cfs_rq); - tg = se->my_q->tg; + tg = cfs_rq->tg; /* * W = @wg + \Sum rw_j */ - W = wg + calc_tg_weight(tg, se->my_q); + W = wg + atomic_long_read(&tg->load_avg); + + /* Ensure \Sum rw_j >= rw_i */ + W -= cfs_rq->tg_load_avg_contrib; + W += w; /* * w = rw_i + @wl */ - w = cfs_rq_load_avg(se->my_q) + wl; + w += wl; /* * wl = S * s'_i; see (2) -- cgit v1.2.3 From 470f47fcf2a5f9c22081c1c4708e6948e3c2dc13 Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Fri, 8 Jul 2016 01:39:11 +0300 Subject: posix_cpu_timer: Exit early when process has been reaped commit 2c13ce8f6b2f6fd9ba2f9261b1939fc0f62d1307 upstream. Variable "now" seems to be genuinely used unintialized if branch if (CPUCLOCK_PERTHREAD(timer->it_clock)) { is not taken and branch if (unlikely(sighand == NULL)) { is taken. In this case the process has been reaped and the timer is marked as disarmed anyway. So none of the postprocessing of the sample is required. Return right away. Signed-off-by: Alexey Dobriyan Link: http://lkml.kernel.org/r/20160707223911.GA26483@p183.telecom.by Signed-off-by: Thomas Gleixner Signed-off-by: Greg Kroah-Hartman --- kernel/time/posix-cpu-timers.c | 1 + 1 file changed, 1 insertion(+) (limited to 'kernel') diff --git a/kernel/time/posix-cpu-timers.c b/kernel/time/posix-cpu-timers.c index f5e86d282d52..80016b329d94 100644 --- a/kernel/time/posix-cpu-timers.c +++ b/kernel/time/posix-cpu-timers.c @@ -808,6 +808,7 @@ static void posix_cpu_timer_get(struct k_itimer *timer, struct itimerspec *itp) timer->it.cpu.expires = 0; sample_to_timespec(timer->it_clock, timer->it.cpu.expires, &itp->it_value); + return; } else { cpu_timer_sample_group(timer->it_clock, p, &now); unlock_task_sighand(p, &flags); -- cgit v1.2.3